Research Engineer – AI Video Processing & Lip-Sync Accuracy

Job Description:

Aion Voice is seeking a talented Research Engineer to tackle complex challenges in AI video processing, focusing on improving lip-sync accuracy and handling visual obstructions (e.g., head turns or occlusions). This role is at the forefront of AI innovation, combining deep learning, computer vision, and generative AI to advance the field of video localisation and dubbing.

You will collaborate with a multidisciplinary team to develop state-of-the-art solutions and integrate them into our production pipeline, with opportunities to publish research and contribute to the next generation of AI-powered localisation tools.

Key Responsibilities:

1. Algorithm Development:

• Design and optimise AI models to improve lip-sync accuracy

• Research and implement state-of-the-art techniques in computer vision and deep learning.

2. AI Model Training and Testing:

• Train models on large-scale datasets to handle diverse video scenarios.

• Evaluate and refine models to ensure real-time performance and scalability.

3. Integration:

• Collaborate with software engineers to deploy solutions in production pipelines.

• Test and iterate models in real-world use cases.

4. Research and Innovation:

• Stay updated on the latest developments in AI, GANs, and video processing.

• Contribute to technical papers, patents, and conference presentations.

5. Problem Solving:

• Address challenges like occlusion recovery, pose estimation, and temporal consistency in video dubbing.

Required Qualifications:

• Master’s or PhD in Computer Science, Artificial Intelligence, or a related field.

• Strong background in computer vision, deep learning, and generative AI.

• Proficiency in frameworks like PyTorch, TensorFlow, or OpenCV.

• Experience with pose estimation techniques (e.g., MediaPipe, OpenPose).

• Advanced programming skills in Python (or similar).

• Understanding of lip-sync and phoneme-based AI models.

Preferred Qualifications:

• Familiarity with GANs, VAEs, or other generative models.

• Experience with real-time AI pipelines or video processing workflows.

• Published research in AI or related fields (e.g., CVPR, ICCV, SIGGRAPH).

• Knowledge of linguistics or speech synthesis techniques is a plus.

Key Skills and Attributes:

• Innovative Thinker: Able to push boundaries in AI-driven localisation.

• Detail-Oriented: Precision in building and testing models.

• Collaborative: Comfortable working in a cross-functional team.

• Adaptable: Thrives in a fast-paced, problem-solving environment.

What We Offer:

• Competitive salary and benefits.

• Opportunities to publish research and attend global conferences.

• Access to cutting-edge tools and datasets.

• A collaborative, innovative environment where your work drives real-world impact.